library(tidyverse)
library(here)
theme_set(theme_minimal()) 

Dados

Importando os dados

gastos <- read_csv(here("data/dadosCEAP.csv"),
                   progress = FALSE)

adicionando a regiao

gastos <- gastos %>% 
  mutate(regiao = case_when(
    sgUF %in% c("AC", "AP", "AM", "PA", "RO", "RR", "TO") ~ "Norte",
    sgUF %in% c("AL", "BA", "CE", "MA", "PB", "PE", "PI", "RN", "SE") ~ "Nordeste",
    sgUF %in% c("DF", "GO", "MT", "MS") ~ "Centro-Oeste",
    sgUF %in% c("ES", "MG", "RJ", "SP") ~ "Sudeste",
    sgUF %in% c("PR", "RS", "SC") ~ "Sul"
  ))

Perguntas

Quais estados mais utilizam a CEAP com despesas com combustíveis?

gastos %>% 
  na.omit() %>% 
  filter(tipoDespesa == "COMBUSTÍVEIS E LUBRIFICANTES.") %>% 
  group_by(sgUF, regiao) %>% 
  summarise(total = sum(valorLíquido)) %>% 
  ungroup() %>% 
  arrange(-total) %>% 
  ggplot(aes(x = reorder(sgUF, total), 
             y = total,
             fill = regiao)) +
  geom_col() +
  facet_wrap(~ regiao,
             scales = "free")

verificar se a quantidade de deputados por estado afeta esse total

gastos %>% 
  na.omit() %>% 
  filter(tipoDespesa == "COMBUSTÍVEIS E LUBRIFICANTES.") %>% 
  group_by(sgUF, regiao) %>% 
  mutate(total = sum(valorLíquido)) %>% 
  select(sgUF, regiao, nomeParlamentar, idCadastro, total) %>% 
  unique() %>%
  mutate(quantidade_deputados = n()) %>% 
  unique() %>% 
  ggplot(aes(x = quantidade_deputados,
             y = total,
             colour = regiao)) +
  geom_point()

gastos %>% 
  na.omit() %>% 
  filter(tipoDespesa == "COMBUSTÍVEIS E LUBRIFICANTES.") %>% 
  group_by(sgUF, regiao) %>% 
  mutate(total = sum(valorLíquido)) %>% 
  select(sgUF, regiao, nomeParlamentar, idCadastro, total) %>% 
  unique() %>%
  mutate(quantidade_deputados = n()) %>% 
  unique() %>%
  cor(.,
      x = quantidade_deputados,
      y = total,
      method = "pearson")
a condição tem comprimento > 1 e somente o primeiro elemento será usadoError in cor(., x = quantidade_deputados, y = total, method = "pearson") : 
  invalid 'use' argument
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